Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    listing items or examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     довольно
    0.58
     átomos
    0.53
     Když
    0.53
     berühm
    0.52
     kebanyakan
    0.50
     ಅನೇಕ
    0.47
     ziemlich
    0.46
     často
    0.46
     jūs
    0.46
     invaders
    0.46
    POSITIVE LOGITS
     including
    0.63
     within
    0.57
    including
    0.57
     включая
    0.54
     včetně
    0.52
     TBA
    0.52
     কমপক্ষে
    0.50
    內
    0.50
     with
    0.50
     Including
    0.49
    Act Density 0.079%

    No Known Activations